Metraipolis › archive › dc_fe358ca7ac22

Where Reliability Lives: Experimental Localisation of Behavioural Properties in an Agent System — arXiv:2609.03192

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03192
License (as archived)
CC0-1.0
Archived
2026-10-17T01:02:58.824Z
SHA-256 of the archived text
c21f2bfc2628525ad8268b170d50a51677d2436eae02cd86b84cadbe23b07ea9
Stable URL of this page
https://metraipolis.com/documento/dc_fe358ca7ac22

How to cite

Where Reliability Lives: Experimental Localisation of Behavioural Properties in an Agent System — arXiv:2609.03192 — arXiv (en), https://arxiv.org/abs/2609.03192 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe358ca7ac22 (Metraipolis archive dc_fe358ca7ac22, sha256 c21f2bfc2628525ad8268b170d50a51677d2436eae02cd86b84cadbe23b07ea9)
BibTeX
@misc{dcfe358ca7ac22,
  title = {Where Reliability Lives: Experimental Localisation of Behavioural Properties in an Agent System — arXiv:2609.03192},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03192},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe358ca7ac22; sha256 c21f2bfc2628525ad8268b170d50a51677d2436eae02cd86b84cadbe23b07ea9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03192. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reliability claims about agentic systems implicitly locate each property somewhere: in the model, or in the machinery around it. We built a system where that location is an experimental question. The subject is a persistent simulated settlement whose authoritative append-only ledger adjudicates every attempted act against world state; accepted history is the only reality. Mind, institution and world were separated before any experiment. Holding cognition fixed, we intervened on the institution's epistemic mechanisms (evidence provenance, belief availability, physical-evidence legibility); preregistered experiments refuted our central prediction twice, in opposite directions. A registered falsifier then supplied the input the geometry had denied the belief channel, a staged veridical first-hand witness, and its marginal value, non-positive throughout the witness-free phases, turned positive: 9 of 11 seeds, zero added false attribution. Holding institutional enforcement fixed, we intervened on cognition four ways: ablating the native minds' machinery, killing and resetting them mid-task, substituting a frozen frontier-LLM panel for the entire native cognition, and corrupting beliefs with trusted false testimony. Behaviour changed dramatically: one falsehood cost each trusting run about 900 futile actions and the distrusting arm none. Five pre-declared properties did not move in any tested trajectory: accepted reality stayed singular, invalid attempts were refused with typed reasons, duties outlived their processes, no work was accepted twice, and no false completion was ever accepted (2,581 substituted-panel claims, none false). Our claim is limited to this setting: measured behavioural properties were separable from substantial changes to cognition, established by intervention. One designed world, not a population of institutions; no test of an agent optimising against the institution.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.03192 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T00:22:10.223Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).